Understanding Naive Bayes in the real world
A classifier is a machine learning model that is used to discriminate different objects based on certain features.
Microsoft - Weed out fake marketing leads.
MS wants to connect with potential customers, our marketers and sellers.
people fill out online forms with fake names, gibberish, or even profanity.
Spam detection
A text can occur in a span or not so using a simple text detector will be bad.
But we can use the number of occurrence of each word in spam or not.
Hence we calculate probability of a word in spam
Hence this is a very common problem of mainly categorings things in real world.
Algorithm
1. Calculate Probability of word being a type
2. Calculate Probability of word being not that
3. Then we multiply each of these and the largest value is the answer
Like in this image used to say if a word is related to sports or not
1 is added to every count so prob is not zero
Weather forecast
Calculate the probability of day being particular weather is one of the use cases of Naive Bayes.
Simple Python code
There is no point in reinventing the wheel atm. You can implement a basic one in 3,4 lines of python using sklearn.
Thanks for reading and thank you Ananya Agrawal for helping out.
You can view the thread in Twitter
References
https://scikit-learn.org/stable/modules/naive_bayes.html
https://www.researchgate.net/publication/290685616_Weather_Forecasting_Using_Naive_Bayesian
https://monkeylearn.com/blog/practical-explanation-naive-bayes-classifier/
I am working on a customer feedback tracker visit https://www.featuremonkey.com/ which is a great alternative for canny, hellonext, uservoice which can be used for feature request tracking , internal feedback, public roadmap etc
